Pioneering Predictive Models for Analyzing Educational Inequality: A Comparative Study of Random Forest, XGBoost, and LSTM
International Journal of Inventions in Engineering & Science Technology · 2025
DOI: 10.37648/ijiest.v11i01.003 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Inventions in Engineering & Science Technology, 2025. Verfasst von Murteza Hanoon Tuama und 2 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben.
Abstract (Originalsprache)
Educational inequality is a significant barrier to achieving justice in education around the world (Baker et al. 2020), and this study aims to fill this gap. This type of pattern and trend identification can similarly be developed using complex feature predictive models like Random Forest and XGBoost or LSTM methods. The results showed that this choice, together with the high accuracy (R2=0.9995) and the lowest predictive error (RMSE=0.006), made the model a powerful tool for understanding dynamic trends in inequality. Moreover, this study indeed modified one of the beginners' models using advanced approaches such as missing value imputation and data normalization which increased the credibility of used models. It contributes a new angle to the existing literature which is so far accounted through the lenses of comparative models by systematically comparing the three models. Educational policies rationalised in accordance with a data-driven analysis can take place to redistribute educational resources more effectively and ultimately prove to be more equitably beneficial to educational systems.
Zitieren
APA
Tuama, M. H., Mashloosh, W. M., & Younus, Y. M. (2025). Pioneering Predictive Models for Analyzing Educational Inequality: A Comparative Study of Random Forest, XGBoost, and LSTM. International Journal of Inventions in Engineering & Science Technology. https://doi.org/10.37648/ijiest.v11i01.003
Vancouver
Tuama MH, Mashloosh WM, Younus YM. Pioneering Predictive Models for Analyzing Educational Inequality: A Comparative Study of Random Forest, XGBoost, and LSTM. International Journal of Inventions in Engineering & Science Technology. 2025. doi:10.37648/ijiest.v11i01.003
BibTeX
@article{Tuama2025,
author = {Tuama, Murteza Hanoon and Mashloosh, Wahhab Muslim and Younus, Yasir Mahmood},
title = {Pioneering Predictive Models for Analyzing Educational Inequality: A Comparative Study of Random Forest, XGBoost, and LSTM},
journal = {International Journal of Inventions in Engineering & Science Technology},
year = {2025},
doi = {10.37648/ijiest.v11i01.003}
}
EUVIMED